Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385612921> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4385612921 endingPage "101967" @default.
- W4385612921 startingPage "101967" @default.
- W4385612921 abstract "Existing multi-view object classification algorithms usually rely on sufficient labeled multi-view objects, which substantially restricts their scalability to novel classes with few annotated training samples in real-world applications. Aiming to go beyond these limitations, we explore a novel yet challenging task, few-shot multi-view object classification (FS-MVOC), which expects the network to build its classification ability efficiently based on limited labeled multi-view objects. To this end, we design a dual augmentation network (DANet) to provide excellent performance for the under-explored FS-MVOC task. On the one hand, we employ an attention-guided multi-view representation augmentation (AMRA) strategy to help the model focus on salient features and suppress unnecessary ones on multiple views of multi-view objects, resulting in more discriminative multi-view representations. On the other hand, during the meta-training stage, we adopt the category prototype augmentation (CPA) strategy to improve the class-representativeness of each prototype and increase the inter-prototype difference by injecting Gaussian noise in the deep feature space. Extensive experiments on the benchmark datasets (Meta-ModelNet and Meta-ShapeNet) indicate the effectiveness and robustness of DANet." @default.
- W4385612921 created "2023-08-07" @default.
- W4385612921 creator A5024121467 @default.
- W4385612921 creator A5036030375 @default.
- W4385612921 creator A5046690683 @default.
- W4385612921 creator A5061046810 @default.
- W4385612921 creator A5076216145 @default.
- W4385612921 date "2023-12-01" @default.
- W4385612921 modified "2023-10-10" @default.
- W4385612921 title "Few-shot multi-view object classification via dual augmentation network" @default.
- W4385612921 cites W1920022804 @default.
- W4385612921 cites W2790362762 @default.
- W4385612921 cites W2798836702 @default.
- W4385612921 cites W2799162093 @default.
- W4385612921 cites W2884585870 @default.
- W4385612921 cites W2905173041 @default.
- W4385612921 cites W2944006115 @default.
- W4385612921 cites W2964105864 @default.
- W4385612921 cites W2976674591 @default.
- W4385612921 cites W2985720528 @default.
- W4385612921 cites W3034652543 @default.
- W4385612921 cites W3035541121 @default.
- W4385612921 cites W3108975329 @default.
- W4385612921 cites W3115567406 @default.
- W4385612921 cites W3126909200 @default.
- W4385612921 cites W3164880353 @default.
- W4385612921 cites W3168470487 @default.
- W4385612921 cites W3173438721 @default.
- W4385612921 cites W3178686235 @default.
- W4385612921 cites W3205249428 @default.
- W4385612921 cites W3205407101 @default.
- W4385612921 cites W3205493274 @default.
- W4385612921 cites W4214562728 @default.
- W4385612921 doi "https://doi.org/10.1016/j.inffus.2023.101967" @default.
- W4385612921 hasPublicationYear "2023" @default.
- W4385612921 type Work @default.
- W4385612921 citedByCount "0" @default.
- W4385612921 crossrefType "journal-article" @default.
- W4385612921 hasAuthorship W4385612921A5024121467 @default.
- W4385612921 hasAuthorship W4385612921A5036030375 @default.
- W4385612921 hasAuthorship W4385612921A5046690683 @default.
- W4385612921 hasAuthorship W4385612921A5061046810 @default.
- W4385612921 hasAuthorship W4385612921A5076216145 @default.
- W4385612921 hasConcept C104317684 @default.
- W4385612921 hasConcept C119857082 @default.
- W4385612921 hasConcept C153180895 @default.
- W4385612921 hasConcept C154945302 @default.
- W4385612921 hasConcept C185592680 @default.
- W4385612921 hasConcept C2780719617 @default.
- W4385612921 hasConcept C2781238097 @default.
- W4385612921 hasConcept C41008148 @default.
- W4385612921 hasConcept C48044578 @default.
- W4385612921 hasConcept C55493867 @default.
- W4385612921 hasConcept C63479239 @default.
- W4385612921 hasConcept C77088390 @default.
- W4385612921 hasConcept C97931131 @default.
- W4385612921 hasConceptScore W4385612921C104317684 @default.
- W4385612921 hasConceptScore W4385612921C119857082 @default.
- W4385612921 hasConceptScore W4385612921C153180895 @default.
- W4385612921 hasConceptScore W4385612921C154945302 @default.
- W4385612921 hasConceptScore W4385612921C185592680 @default.
- W4385612921 hasConceptScore W4385612921C2780719617 @default.
- W4385612921 hasConceptScore W4385612921C2781238097 @default.
- W4385612921 hasConceptScore W4385612921C41008148 @default.
- W4385612921 hasConceptScore W4385612921C48044578 @default.
- W4385612921 hasConceptScore W4385612921C55493867 @default.
- W4385612921 hasConceptScore W4385612921C63479239 @default.
- W4385612921 hasConceptScore W4385612921C77088390 @default.
- W4385612921 hasConceptScore W4385612921C97931131 @default.
- W4385612921 hasFunder F4320318547 @default.
- W4385612921 hasFunder F4320321001 @default.
- W4385612921 hasLocation W43856129211 @default.
- W4385612921 hasOpenAccess W4385612921 @default.
- W4385612921 hasPrimaryLocation W43856129211 @default.
- W4385612921 hasRelatedWork W1972656095 @default.
- W4385612921 hasRelatedWork W2024160000 @default.
- W4385612921 hasRelatedWork W2061273563 @default.
- W4385612921 hasRelatedWork W2285052147 @default.
- W4385612921 hasRelatedWork W2729514902 @default.
- W4385612921 hasRelatedWork W2743258233 @default.
- W4385612921 hasRelatedWork W2773500201 @default.
- W4385612921 hasRelatedWork W2970216048 @default.
- W4385612921 hasRelatedWork W2998168123 @default.
- W4385612921 hasRelatedWork W4287995534 @default.
- W4385612921 hasVolume "100" @default.
- W4385612921 isParatext "false" @default.
- W4385612921 isRetracted "false" @default.
- W4385612921 workType "article" @default.